Classification of underground engineering surrounding rock based on Gaussian cloud model

Abstract

Based on the Gaussian cloud model, an integrative evaluation method for the stability classification of surrounding rock was presented. Selecting five factors, i.e. rock quality designation, uniaxial compressive strengthen, integrality coefficient, strengthen coefficient of structural plane and seepage measurement of groundwater to be the evaluation indicators. According to the Gaussian cloud model and the information entropy theory, the data were normalized and the comprehensive certainty was calculated, then a Gaussian cloud model was obtained to classify the stability classification of surrounding rock. 14 samples of the first stage project in Guangzhou pump accumulator electricity station and 16 samples produced by the interpolation method were taken as the training samples. 12 samples of the second stage project were selected to verify the model. Compared with the artificial neural network (ANN) method and support vector machine (SVM) method, the results show the gauss cloud method has excellent performance and high prediction accuracy, and the method is of practical value, can be applied to evaluate the stability of surrounding rock in underground engineering.